CtrlK
BlogDocsLog inGet started
Tessl Logo

azsdk-common-pipeline-analysis

Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdk_analyze_pipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in CI", "analyze pipeline", "debug SDK pipeline". DO NOT USE FOR: local build issues without pipeline context, API design review, SDK publishing, applying code fixes (instead use azsdk-common-pipeline-fixer). INVOKES: azure-sdk-mcp:azsdk_analyze_pipeline, azure-sdk-mcp:azsdk_get_pipeline_llm_artifacts, azure-sdk-mcp:azsdk_get_failed_test_run_data, azure-sdk-mcp:azsdk_get_failed_test_case_data, azure-sdk-mcp:azsdk_get_pr_checks, azure-sdk-mcp:azsdk_get_pipeline_status.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable instruction skill with a clear sequenced workflow and good error-recovery guidance. Its main defect is that the two referenced reference files are absent from the bundle, breaking the progressive-disclosure navigation it otherwise sets up well.

Suggestions

Add the missing references/output-format.md and references/failure-patterns.md files to the bundle so the inline links resolve, or inline the essential content and drop the dead references.

Add an explicit validation checkpoint in the Steps (e.g., 'Confirm failed_pipeline_tests is non-empty before fetching per-file details') to lift workflow clarity toward a 5.

Remove the redundant restatement of 'does NOT apply fixes' between the overview and the Rules section to tighten conciseness.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, conveying tool-specific return shapes and parameters that Claude would not otherwise know; the only trim is a mild repetition of 'does NOT apply fixes' across the overview and Rules.

4 / 5

Actionability

Guidance is fully executable for an MCP-tool skill: exact tool names, exact parameters ('failedTestRunsPath' set to 'artifact_file_path', 'testCaseTitle'), return-value structure, and a recommended per-file vs per-test call strategy.

5 / 5

Workflow Clarity

Six numbered steps (Identify → Analyze → Fetch → Categorize → Diagnose → Report) give a clear sequence, and the Troubleshooting section provides error-recovery feedback loops; it lacks an explicit validate-checkpoint inside the main flow, keeping it just below a 5.

4 / 5

Progressive Disclosure

The body is well-structured and signals one-level-deep references clearly ('[output format](references/output-format.md)', '[failure patterns](references/failure-patterns.md)'), but no references/ directory or files exist in the bundle, so those links are dead and the disclosure fails to deliver its referenced content.

3 / 5

Total

16

/

20

Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, model description: third-person voice, concrete actions, explicit trigger phrases, and clear boundary guidance against a sibling skill. The only minor gap is that the action list is slightly less exhaustive than the top specificity anchor.

DimensionReasoningScore

Specificity

Names the domain and multiple concrete actions ('Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis', 'define the required output format', 'interprets and formats'), but stops just short of the comprehensive multi-action list that defines a 5.

4 / 5

Completeness

It explicitly answers both 'what' (analyze pipeline failures into a structured diagnosis, define output format) and 'when' via concrete 'USE FOR' trigger phrases, plus a 'DO NOT USE FOR' boundary clause.

5 / 5

Trigger Term Quality

The 'USE FOR' clause supplies natural user phrases ('pipeline failed', 'build failure', 'CI check failing', 'tests failing in CI', 'analyze pipeline', 'debug SDK pipeline') covering synonyms and common phrasings a user would actually say.

5 / 5

Distinctiveness Conflict Risk

The niche is narrow (Azure SDK CI/CD pipeline analysis), triggers are distinct, and 'DO NOT USE FOR ... applying code fixes (instead use azsdk-common-pipeline-fixer)' explicitly disambiguates from the sibling fixer skill, minimizing conflict.

5 / 5

Total

19

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 4 missing

Warning

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

14

/

16

Passed

Repository
Azure/azure-sdk-for-net
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.